InWorld / README.md

linux-2026

Refresh model card with shared branding, navigation and contact

6f432ab verified 8 days ago

9.31 kB

---
license: other
license_name: ltx-2-community
license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x
pipeline_tag: image-to-video
tags:
  - video-generation
  - audio-video-generation
  - multi-reference
  - video-continuation
  - world-model
  - murea
---
<div align="center">

<a href="https://murea.ai/"><img src="https://huggingface.co/MureaLabs/InWorld/resolve/main/assets/readme-banner.png" alt="Murea-InWorld — From imagination to living worlds" width="100%"></a>

# Murea-Fast

**From imagination to living worlds with agents and fast video generation.**

[![Website](https://img.shields.io/badge/Website-murea.ai-207D74?style=for-the-badge)](https://murea.ai/)
[![Paper PDF](https://img.shields.io/badge/Paper-PDF-465D86?style=for-the-badge)](https://murea.ai/page/paper/InWorld-technical-report.pdf)
[![GitHub code](https://img.shields.io/badge/Code-GitHub-182635?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Murea-Labs/InWorld)
[![Hugging Face weights](https://img.shields.io/badge/Weights-Murea--Fast-C18B2E?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/MureaLabs/InWorld)
[![Code license](https://img.shields.io/badge/Code_License-Apache--2.0-526578?style=for-the-badge)](https://github.com/Murea-Labs/InWorld/blob/main/LICENSE)

🎬 [Demo](#demo) · 📦 [Checkpoint](#released-checkpoint) · 🚀 [Get started](#download-and-run) · 🌏 [中文简介](#中文简介) · ✉️ [Contact](mailto:labs@murea.ai)

</div>

Murea-InWorld turns actions and imagination into audiovisual stories. **Murea-Mind** plans each story beat, maintains explicit world memory, and checks generated observations. **Murea-Fast** brings those plans to life as video with synchronized sound, conditioned on text and ordered visual references.

This repository hosts the released **Murea-Fast checkpoint**. The inference service, Murea-Mind application, tests, and deployment instructions are available in the [code repository](https://github.com/Murea-Labs/InWorld). Murea-Pro is evaluated in the technical report; its weights are not included in this release.

<a name="demo"></a>

## 🎬 Demo

<video controls playsinline preload="none" poster="https://murea.ai/page/assets/img/inworld-demo-poster.jpg" width="100%" src="https://github.com/user-attachments/assets/2617c0f3-ded2-4a8f-81bb-b77095c92b0e"></video>

[Watch the storytelling demo](https://github.com/user-attachments/assets/2617c0f3-ded2-4a8f-81bb-b77095c92b0e) · [Explore more worlds](https://murea.ai/#motion)

<a name="highlights"></a>

## ✨ Highlights

- **Multi-reference audiovisual generation:** use ordered references for characters, objects, and locations, then describe actions and dialogue in the prompt.
- **Video with synchronized sound:** generate audiovisual clips with an 8-step distilled sampler.
- **Continuation:** extend a clip from a clean latent prefix derived from its last frames.
- **Interactive worlds with Murea-Mind:** turn player actions into a continuing story with persistent entities, branching histories, and shared co-op adventures.

<a name="released-checkpoint"></a>

## 📦 Released checkpoint

| Item | Details |
| --- | --- |
| Model | Murea-Fast |
| File | [`murea-fast.safetensors`](https://huggingface.co/MureaLabs/InWorld/blob/main/murea-fast.safetensors) |
| File size | 42,018,192,440 bytes, approximately 42.02 GB |
| Sampling | 8 steps |
| Validated output setting | 1280 × 704 pixels, 24 fps |
| Example clip | 121 frames, approximately 5 seconds |
| Continuation | 17-frame prefix; new video frames are generated after the prefix |
| Runtime | The Murea-Fast service in the [GitHub repository](https://github.com/Murea-Labs/InWorld/tree/main/inference) |

SHA-256:

```text
1a2c0d8e23032994b52f2c67e14c930d3be8224f321c51353f0a2954ccbb9385
```

<a name="download-and-run"></a>

## 🚀 Download and run

### 1. Download the weights

```bash
python -m pip install -U huggingface_hub
hf download MureaLabs/InWorld murea-fast.safetensors --local-dir ./weights
```

### 2. Get the inference code

```bash
git clone https://github.com/Murea-Labs/InWorld.git
cd InWorld/inference
```

Follow the [deployment guide](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/deployment.md) to install the GPU environment and obtain the required tokenizer, text encoder, connectors, audio/video decoders, and vocoder. The checkpoint alone is not a complete inference installation.

Set the absolute `python`, `model_dir`, `checkpoint`, and `runtime_dir` paths in `configs/single-gpu.json`. Set `checkpoint` to the downloaded `murea-fast.safetensors` file. Choose a configuration appropriate for the available GPUs and memory.

After completing the environment and component setup:

```bash
bash scripts/murea-fast verify /absolute/path/to/murea-fast.safetensors --sha256
bash scripts/murea-fast prepare --config configs/single-gpu.json
bash scripts/murea-fast start --config configs/single-gpu.json
curl --fail http://127.0.0.1:30260/health
```

For reference-conditioned generation and continuation, use the [inference quick start](https://github.com/Murea-Labs/InWorld/blob/main/inference/README.md#quick-start) and [HTTP API reference](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/api.md). To play stories in the browser, follow the [Murea-Mind quick start](https://github.com/Murea-Labs/InWorld/blob/main/agent/README.md#quick-start).

<a name="evaluation"></a>

## 📊 Evaluation

The technical report reports the following results for Murea-Fast:

| Benchmark | Metric | Score |
| --- | --- | ---: |
| OpenS2V-Eval | Total | 64.98 |
| OS2V-Pro | Aggregate | 69.9 |

See the [technical report](https://murea.ai/page/paper/InWorld-technical-report.pdf) and [project results](https://murea.ai/#results) for the evaluation protocols and comparisons.

<a name="hardware-and-practical-limits"></a>

## 🖥️ Hardware and practical limits

The released inference service has been validated on NVIDIA H20 GPUs in one-GPU and four-GPU configurations. Runtime and memory requirements depend on reference image sizes, clip length, parallelism, and software settings. Consult the [measured performance and memory results](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/performance.md) before choosing hardware.

- The published checks cover 5-second clips on one H20 and clips up to approximately 20 seconds on four 141 GB H20 GPUs. These results do not establish compatibility with smaller-memory GPUs.
- Continuation regenerates audio; continuous speech and sound across clip boundaries are not guaranteed.
- Multiple subjects can merge or lose identity, and long stories can drift. The available deployment checks do not establish quality across all prompts or worlds.
- The current service does not support frame interpolation or upscaling. Experimental acceleration settings need separate validation.

<a name="中文简介"></a>

## 🌏 中文简介

**Murea-InWorld** 将文字行动与参考图像转化为持续发展的视听故事：**Murea-Mind** 负责世界记忆、剧情规划与生成结果检查，**Murea-Fast** 负责生成带同步声音的视频。

本模型仓库发布的是 **Murea-Fast** 权重 `murea-fast.safetensors`；Murea-Mind、推理服务和完整使用文档位于 [GitHub 代码仓库](https://github.com/Murea-Labs/InWorld)。论文中评测的 Murea-Pro 权重不包含在本次发布中。

- 支持有序多参考图条件、8 步蒸馏生成和视频续接。
- 已验证的输出设置为 1280 × 704、24 fps；显存与耗时请参阅实测记录。
- 下载权重后，还需按部署文档安装运行环境和配套组件。
- 续接时音频会重新生成，跨片段的语音和声音连续性不作保证。

[中文部署说明](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/deployment_zh.md) · [中文推理指南](https://github.com/Murea-Labs/InWorld/blob/main/inference/README_zh.md) · [Murea-Mind 中文说明](https://github.com/Murea-Labs/InWorld/blob/main/agent/README_zh.md)

<a name="license"></a>

## 📜 License

The **InWorld code** is released under [Apache License 2.0](https://github.com/Murea-Labs/InWorld/blob/main/LICENSE).

The **Murea-Fast weights and required base components** are governed by the [LTX-2.x Community License Agreement](https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x), as documented in the repository's [provenance and license notice](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/provenance.md#licenses). The code license does not replace the model-weight license. See the linked agreement for its use and redistribution terms.

<a name="citation"></a>

## 📚 Citation

```bibtex
@techreport{murealabs2026inworld,
  title       = {InWorld: From Imagination to Living Worlds with Agents and Fast Video Generation},
  author      = {{Murea Labs}},
  institution = {Murea Labs},
  year        = {2026},
  url         = {https://murea.ai/page/paper/InWorld-technical-report.pdf}
}
```

<a name="contact"></a>

## ✉️ Contact

Email: [labs@murea.ai](mailto:labs@murea.ai)

Visit the [project website](https://murea.ai/) or open an [issue in the code repository](https://github.com/Murea-Labs/InWorld/issues) for questions and reproducible bug reports.

	---
	license: other
	license_name: ltx-2-community
	license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x
	pipeline_tag: image-to-video
	tags:
	- video-generation
	- audio-video-generation
	- multi-reference
	- video-continuation
	- world-model
	- murea
	---

	<div align="center">

	<a href="https://murea.ai/"><img src="https://huggingface.co/MureaLabs/InWorld/resolve/main/assets/readme-banner.png" alt="Murea-InWorld — From imagination to living worlds" width="100%"></a>

	# Murea-Fast

	From imagination to living worlds with agents and fast video generation.

	[![Website](https://img.shields.io/badge/Website-murea.ai-207D74?style=for-the-badge)](https://murea.ai/)
	[![Paper PDF](https://img.shields.io/badge/Paper-PDF-465D86?style=for-the-badge)](https://murea.ai/page/paper/InWorld-technical-report.pdf)
	[![GitHub code](https://img.shields.io/badge/Code-GitHub-182635?style=for-the-badge&logo=github&logoColor=white)](https://github.com/Murea-Labs/InWorld)
	[![Hugging Face weights](https://img.shields.io/badge/Weights-Murea--Fast-C18B2E?style=for-the-badge&logo=huggingface&logoColor=white)](https://huggingface.co/MureaLabs/InWorld)
	[![Code license](https://img.shields.io/badge/Code_License-Apache--2.0-526578?style=for-the-badge)](https://github.com/Murea-Labs/InWorld/blob/main/LICENSE)

	🎬 [Demo](#demo) · 📦 [Checkpoint](#released-checkpoint) · 🚀 [Get started](#download-and-run) · 🌏 [中文简介](#中文简介) · ✉️ [Contact](mailto:labs@murea.ai)

	</div>

	Murea-InWorld turns actions and imagination into audiovisual stories. Murea-Mind plans each story beat, maintains explicit world memory, and checks generated observations. Murea-Fast brings those plans to life as video with synchronized sound, conditioned on text and ordered visual references.

	This repository hosts the released Murea-Fast checkpoint. The inference service, Murea-Mind application, tests, and deployment instructions are available in the [code repository](https://github.com/Murea-Labs/InWorld). Murea-Pro is evaluated in the technical report; its weights are not included in this release.

	<a name="demo"></a>

	## 🎬 Demo

	<video controls playsinline preload="none" poster="https://murea.ai/page/assets/img/inworld-demo-poster.jpg" width="100%" src="https://github.com/user-attachments/assets/2617c0f3-ded2-4a8f-81bb-b77095c92b0e"></video>

	[Watch the storytelling demo](https://github.com/user-attachments/assets/2617c0f3-ded2-4a8f-81bb-b77095c92b0e) · [Explore more worlds](https://murea.ai/#motion)

	<a name="highlights"></a>

	## ✨ Highlights

	- Multi-reference audiovisual generation: use ordered references for characters, objects, and locations, then describe actions and dialogue in the prompt.
	- Video with synchronized sound: generate audiovisual clips with an 8-step distilled sampler.
	- Continuation: extend a clip from a clean latent prefix derived from its last frames.
	- Interactive worlds with Murea-Mind: turn player actions into a continuing story with persistent entities, branching histories, and shared co-op adventures.

	<a name="released-checkpoint"></a>

	## 📦 Released checkpoint

	\| Item \| Details \|
	\| --- \| --- \|
	\| Model \| Murea-Fast \|
	\| File \| [`murea-fast.safetensors`](https://huggingface.co/MureaLabs/InWorld/blob/main/murea-fast.safetensors) \|
	\| File size \| 42,018,192,440 bytes, approximately 42.02 GB \|
	\| Sampling \| 8 steps \|
	\| Validated output setting \| 1280 × 704 pixels, 24 fps \|
	\| Example clip \| 121 frames, approximately 5 seconds \|
	\| Continuation \| 17-frame prefix; new video frames are generated after the prefix \|
	\| Runtime \| The Murea-Fast service in the [GitHub repository](https://github.com/Murea-Labs/InWorld/tree/main/inference) \|

	SHA-256:

	```text
	1a2c0d8e23032994b52f2c67e14c930d3be8224f321c51353f0a2954ccbb9385
	```

	<a name="download-and-run"></a>

	## 🚀 Download and run

	### 1. Download the weights

	```bash
	python -m pip install -U huggingface_hub
	hf download MureaLabs/InWorld murea-fast.safetensors --local-dir ./weights
	```

	### 2. Get the inference code

	```bash
	git clone https://github.com/Murea-Labs/InWorld.git
	cd InWorld/inference
	```

	Follow the [deployment guide](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/deployment.md) to install the GPU environment and obtain the required tokenizer, text encoder, connectors, audio/video decoders, and vocoder. The checkpoint alone is not a complete inference installation.

	Set the absolute `python`, `model_dir`, `checkpoint`, and `runtime_dir` paths in `configs/single-gpu.json`. Set `checkpoint` to the downloaded `murea-fast.safetensors` file. Choose a configuration appropriate for the available GPUs and memory.

	After completing the environment and component setup:

	```bash
	bash scripts/murea-fast verify /absolute/path/to/murea-fast.safetensors --sha256
	bash scripts/murea-fast prepare --config configs/single-gpu.json
	bash scripts/murea-fast start --config configs/single-gpu.json
	curl --fail http://127.0.0.1:30260/health
	```

	For reference-conditioned generation and continuation, use the [inference quick start](https://github.com/Murea-Labs/InWorld/blob/main/inference/README.md#quick-start) and [HTTP API reference](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/api.md). To play stories in the browser, follow the [Murea-Mind quick start](https://github.com/Murea-Labs/InWorld/blob/main/agent/README.md#quick-start).

	<a name="evaluation"></a>

	## 📊 Evaluation

	The technical report reports the following results for Murea-Fast:

	\| Benchmark \| Metric \| Score \|
	\| --- \| --- \| ---: \|
	\| OpenS2V-Eval \| Total \| 64.98 \|
	\| OS2V-Pro \| Aggregate \| 69.9 \|

	See the [technical report](https://murea.ai/page/paper/InWorld-technical-report.pdf) and [project results](https://murea.ai/#results) for the evaluation protocols and comparisons.

	<a name="hardware-and-practical-limits"></a>

	## 🖥️ Hardware and practical limits

	The released inference service has been validated on NVIDIA H20 GPUs in one-GPU and four-GPU configurations. Runtime and memory requirements depend on reference image sizes, clip length, parallelism, and software settings. Consult the [measured performance and memory results](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/performance.md) before choosing hardware.

	- The published checks cover 5-second clips on one H20 and clips up to approximately 20 seconds on four 141 GB H20 GPUs. These results do not establish compatibility with smaller-memory GPUs.
	- Continuation regenerates audio; continuous speech and sound across clip boundaries are not guaranteed.
	- Multiple subjects can merge or lose identity, and long stories can drift. The available deployment checks do not establish quality across all prompts or worlds.
	- The current service does not support frame interpolation or upscaling. Experimental acceleration settings need separate validation.

	<a name="中文简介"></a>

	## 🌏 中文简介

	Murea-InWorld 将文字行动与参考图像转化为持续发展的视听故事：Murea-Mind 负责世界记忆、剧情规划与生成结果检查，Murea-Fast 负责生成带同步声音的视频。

	本模型仓库发布的是 Murea-Fast 权重 `murea-fast.safetensors`；Murea-Mind、推理服务和完整使用文档位于 [GitHub 代码仓库](https://github.com/Murea-Labs/InWorld)。论文中评测的 Murea-Pro 权重不包含在本次发布中。

	- 支持有序多参考图条件、8 步蒸馏生成和视频续接。
	- 已验证的输出设置为 1280 × 704、24 fps；显存与耗时请参阅实测记录。
	- 下载权重后，还需按部署文档安装运行环境和配套组件。
	- 续接时音频会重新生成，跨片段的语音和声音连续性不作保证。

	[中文部署说明](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/deployment_zh.md) · [中文推理指南](https://github.com/Murea-Labs/InWorld/blob/main/inference/README_zh.md) · [Murea-Mind 中文说明](https://github.com/Murea-Labs/InWorld/blob/main/agent/README_zh.md)

	<a name="license"></a>

	## 📜 License

	The InWorld code is released under [Apache License 2.0](https://github.com/Murea-Labs/InWorld/blob/main/LICENSE).

	The Murea-Fast weights and required base components are governed by the [LTX-2.x Community License Agreement](https://github.com/Lightricks/LTX-2/blob/main/LICENSE-2_x), as documented in the repository's [provenance and license notice](https://github.com/Murea-Labs/InWorld/blob/main/inference/docs/provenance.md#licenses). The code license does not replace the model-weight license. See the linked agreement for its use and redistribution terms.

	<a name="citation"></a>

	## 📚 Citation

	```bibtex
	@techreport{murealabs2026inworld,
	title = {InWorld: From Imagination to Living Worlds with Agents and Fast Video Generation},
	author = {{Murea Labs}},
	institution = {Murea Labs},
	year = {2026},
	url = {https://murea.ai/page/paper/InWorld-technical-report.pdf}
	}
	```

	<a name="contact"></a>

	## ✉️ Contact

	Email: [labs@murea.ai](mailto:labs@murea.ai)

	Visit the [project website](https://murea.ai/) or open an [issue in the code repository](https://github.com/Murea-Labs/InWorld/issues) for questions and reproducible bug reports.